Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bf975013034a1115f8c8a3936e4408f41922e1690d80e80abd6ce9bc459b963
+oid sha256:d1d9aa2c3baed805a78809196705a0ae6f0c64dbdbf0b4dd7d140b5a6b351ff4
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1646778abe43efb0a0bf9e6be2fe9f06c16c4a49d4dddbeafa99b97166aa35fc
+oid sha256:f90867a85b2d0c94463fe677b7440150cfa0b2d395b1c6063467ccaeb940c746
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7d48e35f5c526296adaa10e9d66469e5e182a3bb6ac3751b2fc0413eae9601e
+oid sha256:1cfa03e3a47c1805108924390777c41a5495df6301cd3887ed0c6f069a3d37e3
 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": 0.0053567749467756335,
+  "epoch": 0.006867660188173889,
   "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": 1.6154,
       "step": 35
+    },
+    {
+      "epoch": 0.005494128150539112,
+      "grad_norm": 0.9129773378372192,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.7811,
+      "step": 40
+    },
+    {
+      "epoch": 0.005494128150539112,
+      "eval_loss": 1.7244644165039062,
+      "eval_runtime": 109.0993,
+      "eval_samples_per_second": 28.103,
+      "eval_steps_per_second": 14.051,
+      "step": 40
+    },
+    {
+      "epoch": 0.0061808941693565,
+      "grad_norm": 0.783636748790741,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.5446,
+      "step": 45
+    },
+    {
+      "epoch": 0.006867660188173889,
+      "grad_norm": 0.7290799617767334,
+      "learning_rate": 0.0,
+      "loss": 1.6069,
+      "step": 50
+    },
+    {
+      "epoch": 0.006867660188173889,
+      "eval_loss": 1.721480131149292,
+      "eval_runtime": 108.121,
+      "eval_samples_per_second": 28.357,
+      "eval_steps_per_second": 14.179,
+      "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": 1731927711154176.0,
+  "total_flos": 2207005104144384.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null