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:fbe9d6bd713311be1ea014b49c87fe1f7b56948b47aefea028501bf2294b5568
+oid sha256:aec0150e06fd4c920d6ecfa32bb02016082197fcaaec91e501b67936c6f4eca7
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ee86f4fc124265d240d6fc81348f70c58eb2a33044ffe95e39ea949222e38d2
+oid sha256:e8197e2170161424f4c9dd2d62efdd449f087d7dc5808a8b416392b0c146ce70
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ce94eefe6bc934296e9440e3ceba5c5d028c90b5d9420dfecfac5afb6e3d847
+oid sha256:b5b0ce069d7d7490db4eeac3f821d73fffad63d6ef881d57a34a1acd5cd3d36c
 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": 0.07215541165587419,
+  "epoch": 0.09250693802035152,
   "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": 1.0601,
       "step": 35
+    },
+    {
+      "epoch": 0.07400555041628122,
+      "grad_norm": 2.4328479766845703,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.3083,
+      "step": 40
+    },
+    {
+      "epoch": 0.07400555041628122,
+      "eval_loss": 1.1574206352233887,
+      "eval_runtime": 15.2739,
+      "eval_samples_per_second": 14.927,
+      "eval_steps_per_second": 7.464,
+      "step": 40
+    },
+    {
+      "epoch": 0.08325624421831637,
+      "grad_norm": 1.9595891237258911,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0187,
+      "step": 45
+    },
+    {
+      "epoch": 0.09250693802035152,
+      "grad_norm": 2.1735873222351074,
+      "learning_rate": 0.0,
+      "loss": 1.3124,
+      "step": 50
+    },
+    {
+      "epoch": 0.09250693802035152,
+      "eval_loss": 1.134157419204712,
+      "eval_runtime": 15.1476,
+      "eval_samples_per_second": 15.052,
+      "eval_steps_per_second": 7.526,
+      "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": 6396379586887680.0,
+  "total_flos": 8200486649856000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null