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:c817a4be4a708541c2761946db1bc48b1e027449939c221c809ea8e4871ac0e9
+oid sha256:de0eada55edc88b8ef107d3fdb91261546dde9c2ec7d7d1486fb7addde38421d
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8467d55e6afc3e03a46cf93d82be4a4a3ee6501b5ca7027f092bdd89c61e7910
+oid sha256:737bcb1b0aee8f068edbeee391b29d00c1ab0b36f8e4737eb3d23283c212a17d
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00f9b9752f49f9f52e6605be303590b8adaa339e8456ccb350b68c2878cbc286
+oid sha256:ff21dd7c2b2e61f49a8ec74b626a9e3e3040b1da40e138b6c42f961acba34607
 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": 0.016586921850079744,
+  "epoch": 0.02126528442317916,
   "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": 1.6874,
       "step": 35
+    },
+    {
+      "epoch": 0.01701222753854333,
+      "grad_norm": 0.9528077244758606,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.7516,
+      "step": 40
+    },
+    {
+      "epoch": 0.01701222753854333,
+      "eval_loss": 1.6913409233093262,
+      "eval_runtime": 33.5118,
+      "eval_samples_per_second": 29.542,
+      "eval_steps_per_second": 14.771,
+      "step": 40
+    },
+    {
+      "epoch": 0.019138755980861243,
+      "grad_norm": 0.9097928404808044,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.6374,
+      "step": 45
+    },
+    {
+      "epoch": 0.02126528442317916,
+      "grad_norm": 0.897246241569519,
+      "learning_rate": 0.0,
+      "loss": 1.623,
+      "step": 50
+    },
+    {
+      "epoch": 0.02126528442317916,
+      "eval_loss": 1.6824498176574707,
+      "eval_runtime": 33.2776,
+      "eval_samples_per_second": 29.75,
+      "eval_steps_per_second": 14.875,
+      "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": 1931229435789312.0,
+  "total_flos": 2487576988483584.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null