Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d6fe11faf5d4bff3622a17be29bac1746f1a0f0c4eb29d7c1564a6c15441769
+oid sha256:04aa4ff70ccf0299a011f707e2860b190d5e9b65f17b0179884b5d5bd32a0fe8
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2c51766a90b40d6f0d95efb1ab5b3878246fee82202c70cc6fdcecadc80ee6e
+oid sha256:bbf43132f1e3a932eccf77a792be36d517c273da986142854faa5cf7652700d7
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13ca2970a83da1046610e28620345079236b000fba05f523633c3db13ef9d35b
+oid sha256:79950d6e221cc046a6163e93cbd2f473b5d545d011ca45d93a9eeeea05b9bf99
 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": 1.0942,
       "step": 35
+    },
+    {
+      "epoch": 0.011732785803329178,
+      "grad_norm": 0.32417094707489014,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2064,
+      "step": 40
+    },
+    {
+      "epoch": 0.011732785803329178,
+      "eval_loss": 1.0582767724990845,
+      "eval_runtime": 93.007,
+      "eval_samples_per_second": 15.44,
+      "eval_steps_per_second": 7.72,
+      "step": 40
+    },
+    {
+      "epoch": 0.013199384028745325,
+      "grad_norm": 0.31942957639694214,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.07,
+      "step": 45
+    },
+    {
+      "epoch": 0.014665982254161472,
+      "grad_norm": 0.30771729350090027,
+      "learning_rate": 0.0,
+      "loss": 1.0629,
+      "step": 50
+    },
+    {
+      "epoch": 0.014665982254161472,
+      "eval_loss": 1.0569509267807007,
+      "eval_runtime": 93.3322,
+      "eval_samples_per_second": 15.386,
+      "eval_steps_per_second": 7.693,
+      "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": 6883412382056448.0,
+  "total_flos": 8843877933907968.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null