Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9402db8b1e7e858449d95df05aee91c4af65264a2ccb20f7fbb9d6f832c51fe4
+oid sha256:5be0454c3bbbfa5a8a5cdec575c402f640b64c6d424a0079e8de1c45dc083d16
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:568a4ac82b244ee447867b21b688b60dfc18556dd7037a2b3a6c0a63bdafa110
+oid sha256:5b0a4df7a5859f67f2c99f937d89cf776393d76ed06f7295aad8b6ab7c6f54ca
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b06bd10dd952351e53e2bbf531734b0ff570c32c3537e1b7fc9856c31208a14
+oid sha256:e40f3a00568e9964ba996304723fe16ea1d98277beea91876f4e7aa182335a55
 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": 0.0018373909049150207,
+  "epoch": 0.0023556293652756675,
   "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": 1.5594,
       "step": 35
+    },
+    {
+      "epoch": 0.0018845034922205341,
+      "grad_norm": 0.7471029758453369,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.5405,
+      "step": 40
+    },
+    {
+      "epoch": 0.0018845034922205341,
+      "eval_loss": 1.5304561853408813,
+      "eval_runtime": 431.7149,
+      "eval_samples_per_second": 20.703,
+      "eval_steps_per_second": 10.352,
+      "step": 40
+    },
+    {
+      "epoch": 0.0021200664287481007,
+      "grad_norm": 0.8744756579399109,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.4583,
+      "step": 45
+    },
+    {
+      "epoch": 0.0023556293652756675,
+      "grad_norm": 0.8616583347320557,
+      "learning_rate": 0.0,
+      "loss": 1.4149,
+      "step": 50
+    },
+    {
+      "epoch": 0.0023556293652756675,
+      "eval_loss": 1.5266047716140747,
+      "eval_runtime": 431.9564,
+      "eval_samples_per_second": 20.692,
+      "eval_steps_per_second": 10.346,
+      "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": 4161746974801920.0,
+  "total_flos": 5371318755655680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null