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:fea13678076f3681def9a2376e8e6f636c663f7781272739f3908c6d516aa493
+oid sha256:f93fa2574b48259c37665ea76b86511eb53904c99ac9f412bb789262575db2e0
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6bb542e23c27a45c2bc16d3bf27a79aaf3a82210d70dc3661145015f689103c
+oid sha256:834bd193538e78edeedcf377b42ab2c487ee384b53617c7b7f8c2ec317db37ed
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad5f0eac312b1545ecb7cec2dfaf09849808e8a59aee995ff3546a578309a234
+oid sha256:2f3dfab2f15c077a3bfe1d57e8f4dfb9954e3c582cff3d86c56d618335c8d869
 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": 0.009556481254594462,
+  "epoch": 0.012251899044351875,
   "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": 4.1309,
       "step": 35
+    },
+    {
+      "epoch": 0.0098015192354815,
+      "grad_norm": 4.729028224945068,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.1976,
+      "step": 40
+    },
+    {
+      "epoch": 0.0098015192354815,
+      "eval_loss": 0.9041345119476318,
+      "eval_runtime": 203.9483,
+      "eval_samples_per_second": 8.429,
+      "eval_steps_per_second": 4.217,
+      "step": 40
+    },
+    {
+      "epoch": 0.011026709139916687,
+      "grad_norm": 4.707295894622803,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.6423,
+      "step": 45
+    },
+    {
+      "epoch": 0.012251899044351875,
+      "grad_norm": 6.245633125305176,
+      "learning_rate": 0.0,
+      "loss": 3.305,
+      "step": 50
+    },
+    {
+      "epoch": 0.012251899044351875,
+      "eval_loss": 0.90166175365448,
+      "eval_runtime": 203.8285,
+      "eval_samples_per_second": 8.434,
+      "eval_steps_per_second": 4.219,
+      "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": 1.3670840033869824e+16,
+  "total_flos": 1.75267179921408e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null