Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e4fa46fa6270ad7fada55d75c1b5cad246df0649082eca0fffcca6716d50176
+oid sha256:b88209fdbef1b5c8b168f9b0fb662d671c414553096c33c4e3b23e0f855e092c
 size 604317736

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fb18979348de84c82ad58b8f6cc6a7c1312ff42e36ddd14e263973665f1fcc9
+oid sha256:15292cca1297cf3248670370c0f9be677dcd536949a23192cbe61d34e673f169
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3aef7d20483b14af0dec3dd6e05dc978ec3e9677c14b2ba43d2e45951e4f80d
+oid sha256:04802b99b33b6f56b954f18cfba4aaae1ec7857780ef0227027e02fc45dacd00
 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": 0.0013162446527560981,
+  "epoch": 0.0016874931445591001,
   "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": 0.9521,
       "step": 35
+    },
+    {
+      "epoch": 0.0013499945156472803,
+      "grad_norm": 0.514242947101593,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8311,
+      "step": 40
+    },
+    {
+      "epoch": 0.0013499945156472803,
+      "eval_loss": 0.8587357997894287,
+      "eval_runtime": 1054.0064,
+      "eval_samples_per_second": 11.837,
+      "eval_steps_per_second": 5.918,
+      "step": 40
+    },
+    {
+      "epoch": 0.0015187438301031903,
+      "grad_norm": 0.5288004875183105,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.9434,
+      "step": 45
+    },
+    {
+      "epoch": 0.0016874931445591001,
+      "grad_norm": 0.5019608736038208,
+      "learning_rate": 0.0,
+      "loss": 0.9549,
+      "step": 50
+    },
+    {
+      "epoch": 0.0016874931445591001,
+      "eval_loss": 0.8574675917625427,
+      "eval_runtime": 1053.1167,
+      "eval_samples_per_second": 11.847,
+      "eval_steps_per_second": 5.923,
+      "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": 9446658026766336.0,
+  "total_flos": 1.2174787715530752e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null