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:d44bab309d534558f2a88fc5bec77082677d832262b8ea8183c4662ecb071a74
+oid sha256:a72b710c343c1bab234c81e0a812690c59a2d2f62f0a45b9e7b47b28100c0f3f
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87fc5c8f1dabf643b7ec4146cfcf5aa15d0433791a444535df7e1c4219d4f463
+oid sha256:5ea4df826798f87e3698cefde1c5f7824d789b03ef194c4d1ef415c8d078d3a8
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66681b3c2c391b9b876fc6941e8fa5fa1a4cb33da8286dd076ce1100c7302f23
+oid sha256:b1a90b4b434671ccbbaad96b67e68ec52044e52b7af5de81872343b9377be3b7
 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": 0.1824561403508772,
+  "epoch": 0.23391812865497075,
   "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": 1.3909,
       "step": 35
+    },
+    {
+      "epoch": 0.1871345029239766,
+      "grad_norm": 1.454946756362915,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2174,
+      "step": 40
+    },
+    {
+      "epoch": 0.1871345029239766,
+      "eval_loss": 1.2221190929412842,
+      "eval_runtime": 2.8411,
+      "eval_samples_per_second": 31.678,
+      "eval_steps_per_second": 15.839,
+      "step": 40
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 1.449019193649292,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.265,
+      "step": 45
+    },
+    {
+      "epoch": 0.23391812865497075,
+      "grad_norm": 1.641888976097107,
+      "learning_rate": 0.0,
+      "loss": 1.2708,
+      "step": 50
+    },
+    {
+      "epoch": 0.23391812865497075,
+      "eval_loss": 1.1970882415771484,
+      "eval_runtime": 2.8793,
+      "eval_samples_per_second": 31.258,
+      "eval_steps_per_second": 15.629,
+      "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": 1774023176355840.0,
+  "total_flos": 2279168758775808.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null