Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:581ce7f81c2cb8f4d5034e3d4a401140eb8203dac8f805a749805b50a59a5c15
+oid sha256:280a7ebfe3494e2ddfbadd6ea7e5994a5629459d83ca84dd2f4cfa98a1e5ddb4
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6523aea2c089222d14a2c8e1e59664242dc30c55a296d65c0baa4e962dfcbe04
+oid sha256:536f33ba3e90822500aa7f2ab6fd1d63465d6d7f26c8e653a655d84225efb8f7
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d8279a58a5cef9821626ded9aa7d0eae119be7e26dd038b727f51488cd91178
+oid sha256:6909bc52ea6e4c493a6c5299e06f262d192ced58608fc885adb2c9d3363be451
 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": 0.03175249338489721,
+  "epoch": 0.04070832485243232,
   "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": 1.2442,
       "step": 35
+    },
+    {
+      "epoch": 0.03256665988194586,
+      "grad_norm": 0.7182632684707642,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2216,
+      "step": 40
+    },
+    {
+      "epoch": 0.03256665988194586,
+      "eval_loss": 1.2438228130340576,
+      "eval_runtime": 55.7606,
+      "eval_samples_per_second": 9.29,
+      "eval_steps_per_second": 4.645,
+      "step": 40
+    },
+    {
+      "epoch": 0.03663749236718909,
+      "grad_norm": 0.7580611705780029,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.188,
+      "step": 45
+    },
+    {
+      "epoch": 0.04070832485243232,
+      "grad_norm": 0.7346731424331665,
+      "learning_rate": 0.0,
+      "loss": 1.1845,
+      "step": 50
+    },
+    {
+      "epoch": 0.04070832485243232,
+      "eval_loss": 1.2215094566345215,
+      "eval_runtime": 55.8373,
+      "eval_samples_per_second": 9.277,
+      "eval_steps_per_second": 4.638,
+      "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": 7885428108558336.0,
+  "total_flos": 1.023798677078016e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null