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:f21b1e4aa2158da5b27faaa167ee988e0d36d5ae8f742d5d6cb88e48df7236fa
+oid sha256:27958653c6b24dbe126ef9ff1a34b429daf126cb538016892683e5a4f7317f04
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44523ee47dc5ef2a8b866f34f6d7b814e7bb456749c3e75e94d22cb0d3760ec1
+oid sha256:5899fe4844ffd72e4cd346e2387389e2291e9a5261c8dede104c90087afc5bec
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddf11ecb1ff924f73a487cc31ad96c6d977bdb15b6125e60ccde904e1dc64607
+oid sha256:b3dbd4e34bcf6178455113152cf4ec871fa90f0da6a6af9edd890dfceaf2ede2
 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": 0.0304093567251462,
+  "epoch": 0.03898635477582846,
   "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": 1.6436,
       "step": 35
+    },
+    {
+      "epoch": 0.031189083820662766,
+      "grad_norm": 0.9319704174995422,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.5881,
+      "step": 40
+    },
+    {
+      "epoch": 0.031189083820662766,
+      "eval_loss": 1.6812856197357178,
+      "eval_runtime": 61.0027,
+      "eval_samples_per_second": 8.852,
+      "eval_steps_per_second": 4.426,
+      "step": 40
+    },
+    {
+      "epoch": 0.03508771929824561,
+      "grad_norm": 0.9096583127975464,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.6105,
+      "step": 45
+    },
+    {
+      "epoch": 0.03898635477582846,
+      "grad_norm": 0.9196355938911438,
+      "learning_rate": 0.0,
+      "loss": 1.6305,
+      "step": 50
+    },
+    {
+      "epoch": 0.03898635477582846,
+      "eval_loss": 1.6808922290802002,
+      "eval_runtime": 61.0451,
+      "eval_samples_per_second": 8.846,
+      "eval_steps_per_second": 4.423,
+      "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": 8230560904249344.0,
+  "total_flos": 1.0588755320635392e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null