Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35fd6f1e6f10481c03144aedc7ae4493232a2fcb3d6b00ab071cd3f2b614a7f9
+oid sha256:9d66461bc1c5b1242465f15d0cf9de2e29b4102ff55c2c962315afb68a41ffe3
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8cc16587d5bf671f30ee9b10ba393d84110cf7ddd13504417cae18466dba704
+oid sha256:afeedbb74fdcb841a469c7f0afb127ba64e245941f6747f7a883c214803e5b41
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77d4a2f85e287925aa772d78ee90c648b219eb6da2fba37b6ce70531833a54b4
+oid sha256:fcc1abe4d9922ad920e8e400ca21c6e1621a1cfc5d6b3955d5da6a63d021dcd1
 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": 0.0006139798488664988,
+  "epoch": 0.0007871536523929471,
   "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": 1.1987,
       "step": 35
+    },
+    {
+      "epoch": 0.0006297229219143577,
+      "grad_norm": 3.2700657844543457,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0498,
+      "step": 40
+    },
+    {
+      "epoch": 0.0006297229219143577,
+      "eval_loss": 1.3465092182159424,
+      "eval_runtime": 2258.5376,
+      "eval_samples_per_second": 11.842,
+      "eval_steps_per_second": 5.921,
+      "step": 40
+    },
+    {
+      "epoch": 0.0007084382871536523,
+      "grad_norm": 2.826608657836914,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.127,
+      "step": 45
+    },
+    {
+      "epoch": 0.0007871536523929471,
+      "grad_norm": 3.8614323139190674,
+      "learning_rate": 0.0,
+      "loss": 1.3307,
+      "step": 50
+    },
+    {
+      "epoch": 0.0007871536523929471,
+      "eval_loss": 1.3339468240737915,
+      "eval_runtime": 2260.4672,
+      "eval_samples_per_second": 11.832,
+      "eval_steps_per_second": 5.916,
+      "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": 9386538559340544.0,
+  "total_flos": 1.2114645825355776e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null