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:f48e0626894e35d9f5bc1afda9d1e8c549babcde71fdca1ce4ae668cf7b261b5
+oid sha256:df2405c73a2334d546043039c611cb8a6b6fcc6333ee91a9aa503138dbfaef4b
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5436d0486a233cb0e8b8e96ae2b3a2983974442ca9ceab8d12d4e0bef2060d04
+oid sha256:7913ef770bac5e421c708dbc2a3f7f06d100ef1dae3535e2459459883e719a57
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff383c3aa793f123a0fc6459fec6f96cc38f7f1d05c63f6a375677c86fa2335b
+oid sha256:30a0a1af2e8a5fb71ec2ab727cb154638fb24e9fe4c9f17e8067e5894b0fdd8b
 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": 0.002795248078266946,
+  "epoch": 0.0035836513823935207,
   "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": 1.3943,
       "step": 35
+    },
+    {
+      "epoch": 0.0028669211059148166,
+      "grad_norm": 2.7362568378448486,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2605,
+      "step": 40
+    },
+    {
+      "epoch": 0.0028669211059148166,
+      "eval_loss": 1.339518666267395,
+      "eval_runtime": 177.3424,
+      "eval_samples_per_second": 33.128,
+      "eval_steps_per_second": 16.567,
+      "step": 40
+    },
+    {
+      "epoch": 0.0032252862441541686,
+      "grad_norm": 2.2676689624786377,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.4433,
+      "step": 45
+    },
+    {
+      "epoch": 0.0035836513823935207,
+      "grad_norm": 1.9010828733444214,
+      "learning_rate": 0.0,
+      "loss": 1.369,
+      "step": 50
+    },
+    {
+      "epoch": 0.0035836513823935207,
+      "eval_loss": 1.3369534015655518,
+      "eval_runtime": 177.2715,
+      "eval_samples_per_second": 33.141,
+      "eval_steps_per_second": 16.573,
+      "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": 1003983514632192.0,
+  "total_flos": 1291749490163712.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null