Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:798fc8c8528336828dcdcabbc0113274dcb4a72954ab98a2ce80087f59435f40
+oid sha256:39a37c940a69f207f574fb6bbfb6af2f7d0fe9ef3521db9993fd4d333a9b83bb
 size 1579352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6820cb21f67b30035263da1adb5b9996d596a966a85bdbc362e6f9aaca71d31b
+oid sha256:419852f4ce2e76e967d794877be0ad1bf36dbff9e7146ba17ecdb019a1d8cf4e
 size 857338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea7c9fc858473e67fcc95cec6d27aa0e5576ea602eeb55454097dd9e5e25c4e9
+oid sha256:31c867449f25f6b5ad4348dcd06e044d48ba471d92abe508ea1c8d547e9483fa
 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": 0.002471169686985173,
+  "epoch": 0.0031681662653656063,
   "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": 17.3592,
       "step": 35
+    },
+    {
+      "epoch": 0.002534533012292485,
+      "grad_norm": 782.207763671875,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 15.4835,
+      "step": 40
+    },
+    {
+      "epoch": 0.002534533012292485,
+      "eval_loss": 4.120110511779785,
+      "eval_runtime": 61.7626,
+      "eval_samples_per_second": 107.606,
+      "eval_steps_per_second": 53.803,
+      "step": 40
+    },
+    {
+      "epoch": 0.0028513496388290456,
+      "grad_norm": 630.6594848632812,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 16.2635,
+      "step": 45
+    },
+    {
+      "epoch": 0.0031681662653656063,
+      "grad_norm": 692.5111083984375,
+      "learning_rate": 0.0,
+      "loss": 16.6085,
+      "step": 50
+    },
+    {
+      "epoch": 0.0031681662653656063,
+      "eval_loss": 4.110929489135742,
+      "eval_runtime": 61.5114,
+      "eval_samples_per_second": 108.045,
+      "eval_steps_per_second": 54.023,
+      "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": 86107937046528.0,
+  "total_flos": 110472883863552.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null