Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8c444748db456352583b925b9c084a070f0d4d02b2ade88aed8a5702a18fe90
+oid sha256:869d4198250b9a524fbde43a865675872d8619c389e280f45456bf8791fdea74
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d63c129c05abf6a31d71c591b52b0f2b5e42c947701ca1201ca9207eef5ef6f0
+oid sha256:5deb652e634322469e6391b038f816d494bd8213edf7169699de6824f6f1433d
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d592fbfabcdcf0f0d5483e62271f3e31eb1c315b6c63d18110736fd9d9e900f
+oid sha256:1b08fb4ffac833d6b21bf81b9a92be5ac6e9dadec98494748a02b1879acd6c9d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06521739130434782,
+  "epoch": 0.08361204013377926,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 0.3887,
       "step": 35
+    },
+    {
+      "epoch": 0.06688963210702341,
+      "grad_norm": 0.1731388419866562,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4228,
+      "step": 40
+    },
+    {
+      "epoch": 0.06688963210702341,
+      "eval_loss": 0.35631632804870605,
+      "eval_runtime": 27.3679,
+      "eval_samples_per_second": 9.208,
+      "eval_steps_per_second": 4.604,
+      "step": 40
+    },
+    {
+      "epoch": 0.07525083612040134,
+      "grad_norm": 0.1411808878183365,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3501,
+      "step": 45
+    },
+    {
+      "epoch": 0.08361204013377926,
+      "grad_norm": 0.14091266691684723,
+      "learning_rate": 0.0,
+      "loss": 0.3873,
+      "step": 50
+    },
+    {
+      "epoch": 0.08361204013377926,
+      "eval_loss": 0.35408949851989746,
+      "eval_runtime": 27.3106,
+      "eval_samples_per_second": 9.227,
+      "eval_steps_per_second": 4.614,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.2704244087914496e+16,
+  "total_flos": 1.62874924204032e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null