Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02693a59e9a9d73d8ad499d01f938b99b09eb07177931e2fe787a85e7df26ea7
+oid sha256:ce730e5529b6322582b2d52b0a642b8bd099b7388f770e3a189bab8b30eb7915
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e0aa1ffe7f0662733c2d265de969f794a0cd635ae1c47aa8786ff654799c8a6
+oid sha256:96bb222c008b5c4cc385d23303a17b7d88b51a7cdad3f1c1588a722b754845ef
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbce859b81d414b3d92dbea55be7f0a5f7ddcd9e332e66d8e799719215848c39
+oid sha256:fdf5706e85b6edbcb03c576a7dddedd661da6305a10f177ac363e8e7866c0e0d
 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": 0.0007582164416319151,
+  "epoch": 0.0009720723610665578,
   "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": 1.8186,
       "step": 35
+    },
+    {
+      "epoch": 0.0007776578888532463,
+      "grad_norm": 0.8082664608955383,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.0096,
+      "step": 40
+    },
+    {
+      "epoch": 0.0007776578888532463,
+      "eval_loss": 2.290860891342163,
+      "eval_runtime": 1374.3049,
+      "eval_samples_per_second": 15.759,
+      "eval_steps_per_second": 7.88,
+      "step": 40
+    },
+    {
+      "epoch": 0.000874865124959902,
+      "grad_norm": 1.0085279941558838,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.9027,
+      "step": 45
+    },
+    {
+      "epoch": 0.0009720723610665578,
+      "grad_norm": 0.7571061253547668,
+      "learning_rate": 0.0,
+      "loss": 2.009,
+      "step": 50
+    },
+    {
+      "epoch": 0.0009720723610665578,
+      "eval_loss": 2.2849345207214355,
+      "eval_runtime": 1378.3063,
+      "eval_samples_per_second": 15.713,
+      "eval_steps_per_second": 7.857,
+      "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": 7207144126414848.0,
+  "total_flos": 9202342217908224.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null