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:bb982a562fa0e11073a439fdfc04746777b47902d74ad8af399c5e1c4d161c96
+oid sha256:872228a865a65071fb4aa556f99c826ac21b219e253228e5dbe450cbbd31fa86
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5466508a8c5e7879c9e40ed976491d0c6272b31eb2340dd3195ab750ee9cae36
+oid sha256:8c036538ff39a569035a756e328e5704184a8d4c1022077b2c979ae4616135af
 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": 0.0014875702066387587,
+  "epoch": 0.0019071412905625113,
   "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": 1.4135,
       "step": 35
+    },
+    {
+      "epoch": 0.001525713032450009,
+      "grad_norm": 2.8376808166503906,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.4254,
+      "step": 40
+    },
+    {
+      "epoch": 0.001525713032450009,
+      "eval_loss": 0.3301621973514557,
+      "eval_runtime": 1319.5607,
+      "eval_samples_per_second": 8.366,
+      "eval_steps_per_second": 4.183,
+      "step": 40
+    },
+    {
+      "epoch": 0.0017164271615062602,
+      "grad_norm": 2.7614290714263916,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.3417,
+      "step": 45
+    },
+    {
+      "epoch": 0.0019071412905625113,
+      "grad_norm": 2.561908721923828,
+      "learning_rate": 0.0,
+      "loss": 1.2683,
+      "step": 50
+    },
+    {
+      "epoch": 0.0019071412905625113,
+      "eval_loss": 0.32917287945747375,
+      "eval_runtime": 1316.178,
+      "eval_samples_per_second": 8.387,
+      "eval_steps_per_second": 4.194,
+      "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": 1.3670824330395648e+16,
+  "total_flos": 1.75266978594816e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null