Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:133ecd2923f56e0cb899eeb15c371825105926dc8d38abf03004f4cd53953ca7
+oid sha256:5384dea61cc69083d26f2d451084c94ce6958857217f73dd23258ba7804f5f02
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a17b95c6e13dcf353ba65b7648ed50a9f1f8182c8930f08303b73f55887864d
+oid sha256:d84bfa738247c261ac91b946e4a7a20254ecfe87b24b5f8c36f16bdaf00df7dc
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cfbc0801bd4d766f17422a6f7435f703d09d8f581accc93a6fe45904abe559e
+oid sha256:f34bba95447e0ec764b895aa1b44bf630fd1c25c2065aec5f8a5c165a3d1b571
 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": 0.00249077932653159,
+  "epoch": 0.0031933068288866537,
   "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": 0.2446,
       "step": 35
+    },
+    {
+      "epoch": 0.002554645463109323,
+      "grad_norm": 0.5331754684448242,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2701,
+      "step": 40
+    },
+    {
+      "epoch": 0.002554645463109323,
+      "eval_loss": 0.22728973627090454,
+      "eval_runtime": 538.2542,
+      "eval_samples_per_second": 12.249,
+      "eval_steps_per_second": 6.125,
+      "step": 40
+    },
+    {
+      "epoch": 0.0028739761459979883,
+      "grad_norm": 0.6404672861099243,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2368,
+      "step": 45
+    },
+    {
+      "epoch": 0.0031933068288866537,
+      "grad_norm": 0.6445006132125854,
+      "learning_rate": 0.0,
+      "loss": 0.2254,
+      "step": 50
+    },
+    {
+      "epoch": 0.0031933068288866537,
+      "eval_loss": 0.2246289700269699,
+      "eval_runtime": 538.7991,
+      "eval_samples_per_second": 12.236,
+      "eval_steps_per_second": 6.119,
+      "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": 8924147497304064.0,
+  "total_flos": 1.1513537444708352e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null