Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5195a07da41c50f20077ce33d658cfac667c32e5f27c756b8648e34a5a1be6c0
+oid sha256:9c55b4f354024227ea7bf07553bf332ec8c45dd1446aefc2705fdb53b0dc92bd
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c65ebc3eb7d2a956dccac1c913da9b83159d26d4767de5d5c69173557408818
+oid sha256:1c3b1a40d0c5592f78e81c3afbe120d0ae464b046ec0a24e9640df7e18b11780
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb982c82a551e3a58a95d10f65f011252d6abd765e8ca6964152da3997e170eb
+oid sha256:fcde896debd5fc4f8c5dc2fd2d88b9232545fa70606afc3707973c658c9b8630
 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": 0.011439466158245948,
+  "epoch": 0.014665982254161472,
   "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": 1.6188,
       "step": 35
+    },
+    {
+      "epoch": 0.011732785803329178,
+      "grad_norm": 0.6061598658561707,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.7754,
+      "step": 40
+    },
+    {
+      "epoch": 0.011732785803329178,
+      "eval_loss": 1.586182951927185,
+      "eval_runtime": 47.7566,
+      "eval_samples_per_second": 30.069,
+      "eval_steps_per_second": 15.035,
+      "step": 40
+    },
+    {
+      "epoch": 0.013199384028745325,
+      "grad_norm": 0.5589456558227539,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.5946,
+      "step": 45
+    },
+    {
+      "epoch": 0.014665982254161472,
+      "grad_norm": 0.8638172745704651,
+      "learning_rate": 0.0,
+      "loss": 1.5911,
+      "step": 50
+    },
+    {
+      "epoch": 0.014665982254161472,
+      "eval_loss": 1.584321141242981,
+      "eval_runtime": 47.47,
+      "eval_samples_per_second": 30.251,
+      "eval_steps_per_second": 15.125,
+      "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": 303059020283904.0,
+  "total_flos": 389373298212864.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null