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:a63ff3d4467d2ae83538fda0a4bccd3ffb5a63bdeb03116148d37030a3d1ef07
+oid sha256:99d6cba35de89d50d3ba0fe111d4ee0eff6f613990f9eb76a0c80cf0a20eb2b2
 size 604317736

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:795bf1d08e5ad82e8332781b2541232a3e918a8e7299a2f6a3014e4ed58dc49d
+oid sha256:7c0ac211cf373ac0b070dbe29676dc36b187cecac82d7cd993e1e4bbc01cc34e
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e561009e2ff39b4c9e252526ed009d5bad3c1086f161f5444dce1d8a1097b44c
+oid sha256:ce174ba4b8f73edcef3b7eb4ef018c05e31115d59867afd6987065c65ea84fbb
 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": 0.02666666666666667,
+  "epoch": 0.03418803418803419,
   "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": 2.2319,
       "step": 35
+    },
+    {
+      "epoch": 0.02735042735042735,
+      "grad_norm": 1.7004833221435547,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.1117,
+      "step": 40
+    },
+    {
+      "epoch": 0.02735042735042735,
+      "eval_loss": 2.0498950481414795,
+      "eval_runtime": 39.8629,
+      "eval_samples_per_second": 15.453,
+      "eval_steps_per_second": 7.726,
+      "step": 40
+    },
+    {
+      "epoch": 0.03076923076923077,
+      "grad_norm": 1.8769172430038452,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.9793,
+      "step": 45
+    },
+    {
+      "epoch": 0.03418803418803419,
+      "grad_norm": 1.4272596836090088,
+      "learning_rate": 0.0,
+      "loss": 1.8624,
+      "step": 50
+    },
+    {
+      "epoch": 0.03418803418803419,
+      "eval_loss": 2.0455269813537598,
+      "eval_runtime": 39.299,
+      "eval_samples_per_second": 15.675,
+      "eval_steps_per_second": 7.837,
+      "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": 6840683398692864.0,
+  "total_flos": 8673009309057024.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null