Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ff1ec8b9d99ae32eaf71e01d0d01cdbae3247aeb51c37f8faa8a1261cdea7fc
+oid sha256:4dd105973579a407027bfa7691475b71b7d732da7168f0bd7541a8465c8a0d11
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caa7fbf2d5da7a7c4bbe4b1b0b54f22090c078475539216c3ccc2e9e70cf4282
+oid sha256:b861631d971e441d5ffc19a95b0a112320357fa2e58f934a41d3d5143b4f48b4
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72658da797241b36426c8d0b9214fdce2b55dfcf0b6d9c5224ab1410927cdb32
+oid sha256:bd6bb7384f23b8393fd3a6152042d552bd7e7010760a6e78e99507439e54b2b8
 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": 0.068935041979673,
+  "epoch": 0.08837825894829872,
   "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": 1.2017,
       "step": 35
+    },
+    {
+      "epoch": 0.07070260715863898,
+      "grad_norm": 1.6775568723678589,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.1638,
+      "step": 40
+    },
+    {
+      "epoch": 0.07070260715863898,
+      "eval_loss": 1.2111330032348633,
+      "eval_runtime": 19.0169,
+      "eval_samples_per_second": 12.568,
+      "eval_steps_per_second": 6.31,
+      "step": 40
+    },
+    {
+      "epoch": 0.07954043305346885,
+      "grad_norm": 0.7706012725830078,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0841,
+      "step": 45
+    },
+    {
+      "epoch": 0.08837825894829872,
+      "grad_norm": 0.9315032362937927,
+      "learning_rate": 0.0,
+      "loss": 1.2157,
+      "step": 50
+    },
+    {
+      "epoch": 0.08837825894829872,
+      "eval_loss": 1.2092931270599365,
+      "eval_runtime": 18.9727,
+      "eval_samples_per_second": 12.597,
+      "eval_steps_per_second": 6.325,
+      "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": 8507995541471232.0,
+  "total_flos": 1.1051146382671872e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null