Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c0b0788bbc24e6ffd3d7772d181fd76baf3125f66d3243ca7d9487047a627d3
+oid sha256:b929380023652692de974618502a9e5ce85872bd1cc6489af5e185d3bd541dfc
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f898f8145515c0014185f3b63452c18bc4156d0b19e9bf78dc01f18e4e2eada
+oid sha256:102152473324511aac59260f78bdb2cfa416658491d91862a2408bc6bf22538c
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d84a5cf2454179937316496e4212e2e56502a7858df2afe7855b38d36059da33
+oid sha256:4d00d9dd06e9f93188510a54099e9557d05b4458c16b9422695bf5ba429f63cb
 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": 0.005533484676503973,
+  "epoch": 0.007094211123723042,
   "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": 0.6629,
       "step": 35
+    },
+    {
+      "epoch": 0.0056753688989784334,
+      "grad_norm": 0.7956112027168274,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5828,
+      "step": 40
+    },
+    {
+      "epoch": 0.0056753688989784334,
+      "eval_loss": 0.5920448899269104,
+      "eval_runtime": 86.2489,
+      "eval_samples_per_second": 34.412,
+      "eval_steps_per_second": 17.206,
+      "step": 40
+    },
+    {
+      "epoch": 0.006384790011350738,
+      "grad_norm": 0.7369029521942139,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.613,
+      "step": 45
+    },
+    {
+      "epoch": 0.007094211123723042,
+      "grad_norm": 0.8582677841186523,
+      "learning_rate": 0.0,
+      "loss": 0.5679,
+      "step": 50
+    },
+    {
+      "epoch": 0.007094211123723042,
+      "eval_loss": 0.589560866355896,
+      "eval_runtime": 85.6247,
+      "eval_samples_per_second": 34.663,
+      "eval_steps_per_second": 17.331,
+      "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": 1028332078497792.0,
+  "total_flos": 1323000334909440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null