Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b80d37d5204da0394be31ee90d55b26c01b4c57fe94e4757eec97fc54b0d17c
+oid sha256:cf1db30b5a886e5ed2189db868464f1b20719ab5b8dace806affd7b91819cbaf
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7f73c6a1456690b710ba08736006b4f54dabb76d8f9fda62fb1c2b31a4085fc
+oid sha256:1c84a5c7b336b5636d22ecf52513d1198bf52447d0bb6b87e04bf31c1171aa82
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cbfbff5445caae9f2668acaf55142bb15a402c199154485e79ab39da1e78943
+oid sha256:7092244c60798e1ab03d4fe68ee97ba243124819620dca59a1f7c2ad2682481a
 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": 0.002772298341952338,
+  "epoch": 0.0035542286435286384,
   "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": 2.2589,
       "step": 35
+    },
+    {
+      "epoch": 0.0028433829148229108,
+      "grad_norm": 0.9996164441108704,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.349,
+      "step": 40
+    },
+    {
+      "epoch": 0.0028433829148229108,
+      "eval_loss": 2.2811648845672607,
+      "eval_runtime": 205.6699,
+      "eval_samples_per_second": 28.803,
+      "eval_steps_per_second": 14.402,
+      "step": 40
+    },
+    {
+      "epoch": 0.0031988057791757746,
+      "grad_norm": 1.1183048486709595,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.3303,
+      "step": 45
+    },
+    {
+      "epoch": 0.0035542286435286384,
+      "grad_norm": 1.1674339771270752,
+      "learning_rate": 0.0,
+      "loss": 2.3358,
+      "step": 50
+    },
+    {
+      "epoch": 0.0035542286435286384,
+      "eval_loss": 2.2705209255218506,
+      "eval_runtime": 205.5686,
+      "eval_samples_per_second": 28.818,
+      "eval_steps_per_second": 14.409,
+      "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": 1264763208204288.0,
+  "total_flos": 1621491292569600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null